VDA Projekt

library(readr)
library(tidyverse)
library(forcats)
library(plotly)
library(knitr, warn.conflicts = FALSE, quietly=TRUE)
library(RColorBrewer)
library(stringr)
library(dygraphs)
myPalette <- brewer.pal(8, "YlGn")
vgsales <- read_csv("vgsales.csv")

Rows: 16598 Columns: 11
-- Column specification --------------------------------------------------------------------------------------
Delimiter: ","
chr (5): Name, Platform, Year, Genre, Publisher
dbl (6): Rank, NA_Sales, EU_Sales, JP_Sales, Other_Sales, Global_Sales

i Use `spec()` to retrieve the full column specification for this data.
i Specify the column types or set `show_col_types = FALSE` to quiet this message.

Ältere Plattformen/spiele haben mehr verkäufe bzw Wie hat sich die Anzahl der verkäufe im laufe der jahre entwickelt?

Anzahl der Videospiele aufgelistet nach Platform

grouped <- vgsales  %>% 
  group_by(Platform) %>% 
  summarize(Anzahl =n()) 

ordered <- grouped[order(grouped$Anzahl), decreasing = FALSE]
ordered$Platform <- as_factor(ordered$Platform)


ax <- list(
  title = "Publisher"
)

ay <- list(
  title = "Anzahl"
)
ordered%>%
  plot_ly() %>% 
  add_bars(x=~fct_reorder(Platform,Anzahl, .desc="true"),
           y=~Anzahl,
           name="Game Amount by Platform") %>% 
  layout(title="Game Amount by Platform",
         xaxis = ax,
         yaxis = ay
         
         )

Welche Plattform ist die beste und unterscheidet sich diese nach Region?

grouped <- vgsales  %>% 
  group_by(Platform) %>% 
  summarize(sum(Global_Sales))  %>%
rename(
    Global_Sales = "sum(Global_Sales)"
    )
grouped$Global_Sales<-as_vector(grouped$Global_Sales)
ordered <- grouped[order(grouped$Global_Sales), decreasing = FALSE]
ordered$Platform <- as_factor(ordered$Platform)


ax <- list(
  title = "Platform"
)

ay <- list(
  title = "Global Sales (in mio)"

)


ordered%>%
  plot_ly() %>% 
  add_bars(x=~fct_reorder(Platform,Global_Sales, .desc="true"),
           y=~Global_Sales,
           name="Sales Amount by Platform") %>% 
  layout(title="Sales Amount by Platform",
         xaxis = ax,
         yaxis = ay
         )

● Gibt es Unterschiede in den Regionen/hängt das mit der Anzahl der Einwohner der Region zusammen? (Asian>US>EU)

grouped <- vgsales  %>% 
  group_by(Platform) %>% 
  summarize(sum(EU_Sales))  %>%
rename(
    Global_Sales = "sum(EU_Sales)"
    )
grouped$Global_Sales<-as_vector(grouped$Global_Sales)
ordered <- grouped[order(grouped$Global_Sales), decreasing = FALSE]
ordered$Platform <- as_factor(ordered$Platform)


ax <- list(
  title = "Platform"
)

ay <- list(
  title = "EU Sales (in mio)"

)


ordered%>%
  plot_ly() %>% 
  add_bars(x=~fct_reorder(Platform,Global_Sales, .desc="true"),
           y=~Global_Sales,
           name="EU Sales Amount by Platform") %>% 
  layout(title="EU Sales Amount by Platform",
         xaxis = ax,
         yaxis = ay
         )

ordered%>%
  plot_ly() %>% 
  add_pie(values =~Global_Sales,labels=~Platform,textinfo='label+percent',
           name="EU Sales Amount by Publisher") %>% 
  layout(title="EU Sales Amount by Publisher",
         xaxis = ax,
         yaxis = ay
         )

grouped <- vgsales  %>% 
  group_by(Platform) %>% 
  summarize(sum(NA_Sales))  %>%
rename(
    Global_Sales = "sum(NA_Sales)"
    )
grouped$Global_Sales<-as_vector(grouped$Global_Sales)
ordered <- grouped[order(grouped$Global_Sales), decreasing = FALSE]
ordered$Platform <- as_factor(ordered$Platform)


ax <- list(
  title = "Platform"
)

ay <- list(
  title = "NA Sales (in mio)"

)


ordered%>%
  plot_ly() %>% 
  add_bars(x=~fct_reorder(Platform,Global_Sales, .desc="true"),
           y=~Global_Sales,
           name="NA Sales Amount by Platform") %>% 
  layout(title="NA Sales Amount by Platform",
         xaxis = ax,
         yaxis = ay
         )

ordered%>%
  plot_ly() %>% 
  add_pie(values =~Global_Sales,labels=~Platform,textinfo='label+percent',
           name="NA Sales Amount by Publisher") %>% 
  layout(title="NA Sales Amount by Publisher",
         xaxis = ax,
         yaxis = ay
         )

grouped <- vgsales  %>% 
  group_by(Platform) %>% 
  summarize(sum(JP_Sales))  %>%
rename(
    Global_Sales = "sum(JP_Sales)"
    )
grouped$Global_Sales<-as_vector(grouped$Global_Sales)
ordered <- grouped[order(grouped$Global_Sales), decreasing = FALSE]
ordered$Platform <- as_factor(ordered$Platform)


ax <- list(
  title = "Platform"
)

ay <- list(
  title = "JP Sales (in mio)"

)


ordered%>%
  plot_ly() %>% 
  add_bars(x=~fct_reorder(Platform,Global_Sales, .desc="true"),
           y=~Global_Sales,
           name="JP Sales Amount by Platform") %>% 
  layout(title="JP Sales Amount by Platform",
         xaxis = ax,
         yaxis = ay
         )

ordered%>%
  plot_ly() %>% 
  add_pie(values =~Global_Sales,labels=~Platform,textinfo='label+percent',
           name="JP Sales Amount by Publisher") %>% 
  layout(title="JP Sales Amount by Publisher",
         xaxis = ax,
         yaxis = ay
         )

Bestimmte Entwickler/Publisher häufen sich (Nintendo/EA)

Top Publisher nach Anzahl der Games

grouped <- vgsales  %>% 
  group_by(Publisher) %>% 
  summarize(Anzahl =n()) %>%  
  filter(Anzahl>100) %>% filter(Publisher!="Unknown")

ordered <- grouped[order(grouped$Anzahl), decreasing = FALSE]
ordered$Publisher <-str_remove_all(ordered$Publisher, "Entertainment")
ordered$Publisher <-str_remove_all(ordered$Publisher, "Interactive")
ordered$Publisher <-str_remove_all(ordered$Publisher, "Studios")
ordered$Publisher <- as_factor(ordered$Publisher)


ax <- list(
  title = "Publisher"
)

ay <- list(
  title = "Anzahl"
)
ordered%>%
  plot_ly() %>% 
  add_bars(x=~fct_reorder(Publisher,Anzahl, .desc="true"),
           y=~Anzahl,
           name="Game Amount by Publisher") %>% 
  layout(title="Game Amount by Publisher",
         xaxis = ax,
         yaxis = ay
         
         )

Top Publisher nach Anzahl der Sales

grouped <- vgsales  %>% 
  group_by(Publisher) %>% 
  summarize(Anzahl =n(),sum(Global_Sales)) %>%
  filter(Anzahl>100) %>%
rename(
    Global_Sales = "sum(Global_Sales)"
    )
grouped$Global_Sales<-as_vector(grouped$Global_Sales)
ordered <- grouped[order(grouped$Global_Sales), decreasing = FALSE]
ordered$Publisher <-str_remove_all(ordered$Publisher, "Entertainment")
ordered$Publisher <-str_remove_all(ordered$Publisher, "Interactive")
ordered$Publisher <-str_remove_all(ordered$Publisher, "Studios")
ordered$Publisher <- as_factor(ordered$Publisher)


ax <- list(
  title = "Publisher"
)

ay <- list(
  title = "Global Sales (in mio)"

)


ordered%>%
  plot_ly() %>% 
  add_bars(x=~fct_reorder(Publisher,Global_Sales, .desc="true"),
           y=~Global_Sales,
           name="Sales Amount by Publisher") %>% 
  layout(title="Sales Amount by Publisher",
         xaxis = ax,
         yaxis = ay
         )

● Welche Spiele/Publisher/Genres in welchen Teilen der welt sich häufen (Nintendo in Asien, Shooter in US/EU)

grouped <- vgsales  %>% 
  group_by(Publisher) %>% 
  summarize(Anzahl =n(),sum(EU_Sales)) %>%
  filter(Anzahl>100) %>%
rename(
    Global_Sales = "sum(EU_Sales)"
    )
grouped$Global_Sales<-as_vector(grouped$Global_Sales)
ordered <- grouped[order(grouped$Global_Sales), decreasing = FALSE]
ordered$Publisher <-str_remove_all(ordered$Publisher, "Entertainment")
ordered$Publisher <-str_remove_all(ordered$Publisher, "Interactive")
ordered$Publisher <-str_remove_all(ordered$Publisher, "Studios")
ordered$Publisher <- as_factor(ordered$Publisher)


ax <- list(
  title = "Publisher"
)

ay <- list(
  title = "EU Sales (in mio)"

)

ordered%>%
  plot_ly() %>% 
  add_bars(x=~fct_reorder(Publisher,Global_Sales, .desc="true"),
           y=~Global_Sales,
           name="EU Sales Amount by Platform") %>% 
  layout(title="EU Sales Amount by Platform",
         xaxis = ax,
         yaxis = ay
         )

ordered%>%
  plot_ly() %>% 
  add_pie(values =~Global_Sales,labels=~Publisher,
           name="EU Sales Amount by Publisher") %>% 
  layout(title="EU Sales Amount by Publisher",
         xaxis = ax,
         yaxis = ay
         )

grouped <- vgsales  %>% 
  group_by(Publisher) %>% 
  summarize(Anzahl =n(),sum(NA_Sales)) %>%
  filter(Anzahl>100) %>%
rename(
    Global_Sales = "sum(NA_Sales)"
    )
grouped$Global_Sales<-as_vector(grouped$Global_Sales)
ordered <- grouped[order(grouped$Global_Sales), decreasing = FALSE]
ordered$Publisher <-str_remove_all(ordered$Publisher, "Entertainment")
ordered$Publisher <-str_remove_all(ordered$Publisher, "Interactive")
ordered$Publisher <-str_remove_all(ordered$Publisher, "Studios")
ordered$Publisher <- as_factor(ordered$Publisher)


ax <- list(
  title = "Publisher"
)

ay <- list(
  title = "NA Sales (in mio)"

)

ordered%>%
  plot_ly() %>% 
  add_bars(x=~fct_reorder(Publisher,Global_Sales, .desc="true"),
           y=~Global_Sales,
           name="NA Sales Amount by Platform") %>% 
  layout(title="NA Sales Amount by Platform",
         xaxis = ax,
         yaxis = ay
         )

ordered%>%
  plot_ly() %>% 
  add_pie(values =~Global_Sales,labels=~Publisher,textinfo='label+percent',
           name="NA Sales Amount by Publisher") %>% 
  layout(title="NA Sales Amount by Publisher",
         xaxis = ax,
         yaxis = ay
         )

grouped <- vgsales  %>% 
  group_by(Publisher) %>% 
  summarize(Anzahl =n(),sum(JP_Sales)) %>%
  filter(Anzahl>100) %>%
rename(
    Global_Sales = "sum(JP_Sales)"
    )
grouped$Global_Sales<-as_vector(grouped$Global_Sales)
ordered <- grouped[order(grouped$Global_Sales), decreasing = FALSE]
ordered$Publisher <-str_remove_all(ordered$Publisher, "Entertainment")
ordered$Publisher <-str_remove_all(ordered$Publisher, "Interactive")
ordered$Publisher <-str_remove_all(ordered$Publisher, "Studios")
ordered$Publisher <- as_factor(ordered$Publisher)


ax <- list(
  title = "Publisher"
)

ay <- list(
  title = "JP Sales (in mio)"

)

ordered%>%
  plot_ly() %>% 
  add_bars(x=~fct_reorder(Publisher,Global_Sales, .desc="true"),
           y=~Global_Sales,
           name="JP Sales Amount by Platform") %>% 
  layout(title="JP Sales Amount by Platform",
         xaxis = ax,
         yaxis = ay
         )

ordered%>%
  plot_ly() %>% 
  add_pie(values =~Global_Sales,labels=~Publisher,
           name="JP Sales Amount by Publisher") %>% 
  layout(title="JP Sales Amount by Publisher",
         xaxis = ax,
         yaxis = ay
         )

● Genrenentwicklung über die Jahre

grouped <- vgsales  %>% 
  group_by(Genre) %>% 
  summarize(Anzahl =n())

grouped$Anzahl<-as_vector(grouped$Anzahl)
ordered <- grouped[order(grouped$Anzahl), decreasing = FALSE]
ordered$Genre <- as_factor(ordered$Genre)


ax <- list(
  title = "Genre"
)

ay <- list(
  title = "Anzahl"

)

ordered%>%
  plot_ly() %>% 
  add_bars(x=~fct_reorder(Genre,Anzahl, .desc="true"),
           y=~Anzahl,
           name="Amount by Genre") %>% 
  layout(title="Amount by Genre",
         xaxis = ax,
         yaxis = ay
         )

ordered%>%
  plot_ly() %>% 
  add_pie(values =~Anzahl,labels=~Genre,
           name="Amount by Genre") %>% 
  layout(title="Amount by Genre",
         xaxis = ax,
         yaxis = ay
         )

grouped <- vgsales  %>% 
  group_by(Genre) %>% 
  summarize(sum(Global_Sales))  %>%
rename(
    Global_Sales = "sum(Global_Sales)"
    )
grouped$Global_Sales<-as_vector(grouped$Global_Sales)
ordered <- grouped[order(grouped$Global_Sales), decreasing = FALSE]

ax <- list(
  title = "Genre"
)

ay <- list(
  title = "Sales"

)

ordered%>%
  plot_ly() %>% 
  add_bars(x=~fct_reorder(Genre,Global_Sales, .desc="true"),
           y=~Global_Sales,
           name="Sales by Genre") %>% 
  layout(title="Sales by Genre",
         xaxis = ax,
         yaxis = ay
         )

ordered%>%
  plot_ly() %>% 
  add_pie(values =~Global_Sales,labels=~Genre,
           name="Sales by Genre") %>% 
  layout(title="Sales by Genre",
         xaxis = ax,
         yaxis = ay
        )

grouped <- vgsales  %>% 
  group_by(Genre)
filtered <- grouped %>% select(Year,Genre)
typeof(vgsales)

[1] "list"

typeof(filtered)

[1] "list"

view(filtered)
filtered %>%
plot_ly() %>% 
  add_bars(x=~Year,
           y=~Genre)

dygraph(filtered)

Error in dygraph(filtered) : Unsupported type passed to argument 'data'.

● Gibt es Statistische zusammenhänge zwischen einzelnen Faktoren e.g. Genre -> Sales ● Welche Jahre sind die besten in der Anzahl der releasten games ● Welche Jahre sind die besten in Anzahl Sales pro game (neuer = besser?)